© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3644
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles that indicate actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /remove
    -0.12
    /do
    -0.11
    ings
    -0.11
    /disable
    -0.11
    /use
    -0.09
    tings
    -0.09
    /write
    -0.09
    (er
    -0.09
    /delete
    -0.08
    heimer
    -0.08
    POSITIVE LOGITS
    ly
    0.11
     thereby
    0.10
    /logging
    0.08
     both
    0.08
     perhaps
    0.08
     as
    0.07
     ones
    0.07
     notamment
    0.07
    /loading
    0.07
    both
    0.07
    Activations Density 0.180%

    No Known Activations